mlsanityData to 7 Oct 2026

Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd

arXiv 1807.08407 ↗First posted 23 Jul 2018cs.CVcited by 58

Not on the map. Why?

Abstract (arXiv)

Pedestrian detection in crowded scenes is a challenging problem since the pedestrians often gather together and occlude each other. In this paper, we propose a new occlusion-aware R-CNN (OR-CNN) to improve the detection accuracy in the crowd. Specifically, we design a new aggregation loss to enforce proposals to be close and locate compactly to the corresponding objects. Meanwhile, we use a new part occlusion-aware region of interest (PORoI) pooling unit to replace the RoI pooling layer in order to integrate the prior structure information of human body with visibility prediction into the network to handle occlusion. Our detector is trained in an end-to-end fashion, which achieves state-of-the-art results on three pedestrian detection datasets, i.e., CityPersons, ETH, and INRIA, and performs on-pair with the state-of-the-arts on Caltech.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 18; 2023: 10; 2024: 4; 2025: 4; 2026: 3.

58 papers.

Sort:

  1. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 232
  2. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  3. 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
  4. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 59
  5. 2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
  6. 2021Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)cited by 45
  7. 2021Human De-occlusion: Invisible Perception and Recovery for Humanscited by 31
  8. 2021Instance-wise Occlusion and Depth Orders in Natural Scenescited by 31
  9. 2022Progressive End-to-End Object Detection in Crowded Scenescited by 31
  10. 2022Weakly Aligned Feature Fusion for Multimodal Object Detectioncited by 26
  11. 2021Occlusion Handling in Generic Object Detection: A Reviewcited by 25
  12. 2023VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervisioncited by 19
38 more
  1. 2022Towards Domain Generalization in Object Detectioncited by 16
  2. 2022Deep Learning Serves Traffic Safety Analysis: A Forward-looking Reviewcited by 13
  3. 2024Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenescited by 13
  4. 2021Variational Pedestrian Detectioncited by 10
  5. 2021Holistic Guidance for Occluded Person Re-Identificationcited by 9
  6. 2021BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policiescited by 9
  7. 2022Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyondcited by 8
  8. 2022Beta R-CNN: Looking into Pedestrian Detection from Another Perspectivecited by 8
  9. 2021LLA: Loss-aware Label Assignment for Dense Pedestrian Detectioncited by 7
  10. 20212.5D Visual Relationship Detectioncited by 7
  11. 2021NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detectioncited by 7
  12. 2021Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoUcited by 7
  13. 2023Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Searchcited by 7
  14. 2021Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challengecited by 6
  15. 2022Improving Crowded Object Detection via Copy-Pastecited by 6
  16. 2025SARMAE: Masked Autoencoder for SAR Representation Learningcited by 6
  17. 2022KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondencescited by 5
  18. 2022Occlusion-Aware Instance Segmentation via BiLayer Network Architecturescited by 5
  19. 2022Body-Part Joint Detection and Association via Extended Object Representationcited by 5
  20. 2022Deep Multi-Task Networks For Occluded Pedestrian Pose Estimationcited by 4
  21. 2022Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentationcited by 4
  22. 2022Feature Calibration Network for Occluded Pedestrian Detectioncited by 4
  23. 2023Learning Pedestrian Actions to Ensure Safe Autonomous Drivingcited by 4
  24. 2022Mask Focal Loss: A unifying framework for dense crowd counting with canonical object detection networkscited by 3
  25. 2023Attribute Annotation and Bias Evaluation in Visual Datasets for Autonomous Drivingcited by 3
  26. 2021V2F-Net: Explicit Decomposition of Occluded Pedestrian Detectioncited by 2
  27. 2021Pedestrian Detection by Exemplar-Guided Contrastive Learningcited by 2
  28. 2023BPJDet: Extended Object Representation for Generic Body-Part Joint Detectioncited by 2
  29. 2023Now You See Me: Robust approach to Partial Occlusionscited by 2
  30. 2024YOCO: You Only Calibrate Once for Accurate Extrinsic Parameter in LiDAR-Camera Systemscited by 2
  31. 2025Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detectioncited by 2
  32. 2021You Better Look Twice: a new perspective for designing accurate detectors with reduced computationscited by 1
  33. 2022An Objective Method for Pedestrian Occlusion Level Classificationcited by 1
  34. 2022UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classificationcited by 1
  35. 2023Hardwiring ViT Patch Selectivity into CNNs using Patch Mixingcited by 1
  36. 2024Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completioncited by 1
  37. 2025Density-based Object Detection in Crowded Scenescited by 1
  38. 2026Towards Driver Behavior Understanding: Weakly-Supervised Risk Perception in Driving Scenescited by 1

50 most cited of 58 All 58 (JSON)